ClawHub
Back to skill

Security audit

vx-agent-workflow

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill that teaches token-efficient command patterns and does not install code, persist itself, or hide unrelated behavior.

Before installing, users should understand that this skill will encourage agents to use vx-wrapped commands and compact GitHub/CI queries. If an agent proposes posting issue or PR updates, ensure it has explicit authorization and avoids internal IDs, paths, hostnames, or other sensitive details.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill’s primary purpose is token-efficient command execution, but this section broadens scope into prescriptive workflow and delivery guidance for external systems such as issue trackers and PRs. That creates a cross-boundary instruction surface where an agent may disclose operational details, post to external services, or treat tracker updates as part of execution without explicit user authorization, increasing the risk of unintended data exposure or unauthorized state changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.